UvA-DARE (Digital Academic Repository) Neural Relational Inference for Interacting Systems Neural Relational Inference for Interacting Systems

By T. Fetaya, E. Wang, K.-C. Welling, M. Zemel, Thomas Kipf, Ethan Fetaya, Kuan-Chieh Jackson Wang, Max Welling, Richard S. Zemel. 2018

Subfields: Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Graph Learning

Citations in the corpus

E(n) Equivariant Graph Neural Networks (2021, methodology): “Similarly to (Serviansky et al., 2020; Kipf et al., 2018), we present a simple solution to infer the relations/edges of the graph in our model, even when they are not explicitly provided.”
Towards Causal Representation Learning (2021, background): “among them, modulo the completeness of the variables, and confounding [58, 265, 43, 264, 14, 136].”
On the Binding Problem in Artificial Neural Networks (2020, methodology): “for a fixed number of nodes as in Neural Relational Inference (NRI; Kipf et al., 2018) or adaptively as in Graph Recurrent Attention Networks (GRANs; Liao et al.”
Recurrent Independent Mechanisms (2019, background): “…scenes, and motion-capture data, and multiagent systems (Scarselli et al., 2008; Bronstein et al., 2017; Watters et al., 2017; Raposo et al., 2017; Santoro et al., 2017; Gilmer et al., 2017; Van Steenkiste et al., 2018; Kipf et al., 2018; Battaglia et al., 2018; Tacchetti et al., 2018).”
Stochastic Prediction of Multi-Agent Interactions from Partial Observations (2019, methodology): “In the “neural relational inference” method of Kipf et al. (2018), they infer the interaction graph from trajectories, treating it as a static latent variable in a VAE framework.”
Relational inductive biases, deep learning, and graph networks (2018, methodology): “Recently, a class of models has arisen at the intersection of deep learning and structured approaches, which focuses on approaches for reasoning about explicitly structured data, in particular graphs (e.g. Scarselli et al., 2009b; Bronstein et al., 2017; Gilmer et al., 2017; Wang et al., 2018c; Li e”
Flexible Neural Representation for Physics Prediction (2018, methodology): “To enable a pixel-based end-to-end trainable version of the HRN for use in key computer vision applications, it will be critical to combine our work with adaptations of existing methods (e.g. [54, 23, 15]) for inferring initial (non-hierarchical) scene graphs from LIDAR/RGBD/RGB image or video data.”
Differentiable Physics-informed Graph Networks (2019, background): “…A class of models (Grzeszczuk et al., 1998; Battaglia et al., 2016; Chang et al., 2017; Watters et al., 2017; Sanchez-Gonzalez et al., 2018; Kipf et al., 2018) have been proposed based on the assumption that neural networks can learn complex physical interactions and simulate unseen…”
Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity (2019, methodology): “adapting the graph neural network described in (Kipf et al., 2018).”
Hierarchical Graph Representation Learning with Differentiable Pooling (2018, methodology): “ssiﬁcation Tasks with Edge Features Although the datasets used for experiments do not contain features, DIFFPOOL could be extended to handle such cases. A possible approach is to use a GNN similar to [21]. Note that both the pooling and embedding network are ﬂexible and models incorporating edge fea”
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks (2020, background): “Point cloud data is ubiquitous across many fields, presenting itself in diverse forms such as 3D object scans [21], molecular structures [17], or particle simulations [10].”
Set2Graph: Learning Graphs From Sets (2020, background): “The Neural relational Inference model [12] is another related work that targets learning relations and dynamics of a set of objects in an unsupervised manner.”
Graphite: Iterative Generative Modeling of Graphs (2018, background): “[17] and [21] generate graphs as latent representations learned directly from data.”
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles (2020, background): “Coordination graphs (Bargiacchi et al., 2018; Yang et al., 2018; Grover et al., 2018; Kipf et al., 2018) and explicit communication (Sukhbaatar et al., 2016; Hoshen, 2017; Jiang & Lu, 2018; Singh et al., 2019; Das et al., 2019; Singh et al., 2019; Kim et al., 2019) are studied to model the…”
Relational Forward Models for Multi-Agent Learning (2018, positive): “First, we show that our models can surpass previous top methods on this task (Kipf et al., 2018; Hoshen, 2017), and, crucially, produce intermediate representations that support the social analysis of multi-agent systems: our models explain what drives each agent’s behavior, track how agents…”
Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020, background): “Kipf et al. (2018) proposed a GNN-based VAE model for relational inference for interacting systems.”
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids (2018, result): “Our approach is also complementary to some recent work on learning to discover the interaction graphs (van Steenkiste et al., 2018; Kipf et al., 2018).”
GNNExplainer: Generating Explanations for Graph Neural Networks (2019, background): “To answer these queries, a computationally efﬁcient version of G NN E XPLAINER ’s objective, which we optimize using gradient descent, is as follows: The masking approach is also found in Neural Relational Inference [22], albeit with different motivation and objective.”